Correct DeepSeek review receipt attribution

6-Documentation/wiki/DeepSeek-Review-Process.md

@@ -1,6 +1,6 @@
 # DeepSeek Review Process
 
-> **Source:** [[Home|Wiki Home]] · `5-Applications/tools-scripts/llm/deepseek_review_adapter.py` · `shared-data/artifacts/deepseek_review/`
+> **Source:** [[Home|Wiki Home]] · `shared-data/artifacts/deepseek_review/`
 
 The Research Stack incorporates DeepSeek AI models for formal mathematical
 review and validation of canonical specifications, Lean kernels, and
@@ -9,6 +9,14 @@ of the review pipeline, the receipt schema, and the canonical example
 (prime-gap entropy collapse) shipped under
 `shared-data/artifacts/deepseek_review/`.
 
+Important boundary: the canonical artifacts documented on this page are
+Ollama-compatible review receipts. The tracked
+`5-Applications/tools-scripts/llm/deepseek_review_adapter.py` is a separate
+Anthropic-compatible DeepSeek adapter with its own `schema_version: "1.0"`
+receipt format. Do not use that adapter as the emitter for the
+`ollama_deepseek_review_receipt_v1` schema unless it has first been reconciled
+to this schema.
+
 ---
 
 ## AI-Assisted Mathematical Review
@@ -32,6 +40,23 @@ without re-running the model.
 Receipt filenames are aligned with their answer files by sharing the same
 `<topic>_<model>_<ISO-timestamp>` stem.
 
+### Emitter Boundary
+
+The existing prime-gap receipts were not emitted by
+`5-Applications/tools-scripts/llm/deepseek_review_adapter.py`. That adapter
+targets `https://api.deepseek.com/anthropic`, records `schema_version`,
+`completed_at`, `tokens.{input,output,cache_creation,cache_read}`,
+`response_sha256`, and structured `cached_context_files`, and is suitable for
+Anthropic-compatible DeepSeek reviews.
+
+The artifacts in `shared-data/artifacts/deepseek_review/` instead record the
+Ollama-compatible schema documented below: `schema`, `created_at`, `endpoint`,
+`usage.{prompt_tokens,completion_tokens,total_tokens}`, plain string
+`context_files`, and `answer_sha256`. As of this page, no tracked canonical
+Ollama emitter script has been identified in the repository. Treat the checked
+receipts themselves as the schema authority until such an emitter is added or
+the adapter is reconciled.
+
 ### Receipt Schema
 
 Both receipt schemas are versioned JSON records that track every field needed
@@ -163,7 +188,9 @@ When emitting new review artifacts:
 2. Write the matching receipt alongside it with the same stem and
    `.receipt.json` suffix, using `ollama_deepseek_review_receipt_v1` for the
    primary review and `ollama_deepseek_review_continuation_receipt_v1` for any
-   continuation.
+   continuation. Do not generate these receipts with
+   `5-Applications/tools-scripts/llm/deepseek_review_adapter.py`; it emits a
+   different Anthropic-compatible schema unless explicitly updated.
 3. Populate `context_files` with repo-relative paths to every file consumed
    by the prompt so future agents can reproduce the prompt body. Continuation
    receipts omit `context_files` and `message_keys` records the alternate
@@ -179,10 +206,12 @@ When emitting new review artifacts:
 
 ## Related
 
-- [[Build-System]] — pinned Python interpreter that drives the review adapter
-  and ensures prompt-hash reproducibility across runs.
-- `5-Applications/tools-scripts/llm/deepseek_review_adapter.py` — adapter that
-  emits the receipt + answer pair.
+- [[Build-System]] — pinned Python interpreter for review tooling and
+  prompt-hash reproducibility across runs.
+- `5-Applications/tools-scripts/llm/deepseek_review_adapter.py` —
+  Anthropic-compatible DeepSeek adapter with a different receipt schema; useful
+  as related infrastructure, but not the emitter for the current Ollama-style
+  artifacts.
 - `6-Documentation/docs/distilled/` — canonical specs that reviews validate
   against (e.g. `ArithmeticSpec_Corrected_2026-05-11.md`).
 - `0-Core-Formalism/lean/Semantics/Semantics/HCMMR/Kernels/` — Lean kernels

6-Documentation/wiki/Home.md

@@ -81,4 +81,4 @@
 |---|---|
 | `wiki/DeepSeek-Review-Process.md` | Receipt schema (`ollama_deepseek_review_receipt_v1`), two-stage pipeline (`deepseek-v3.2` + `deepseek-v4-flash` continuation), prime-gap entropy-collapse example |
 | `shared-data/artifacts/deepseek_review/` | Paired answer + receipt artifacts for each review run |
-| `5-Applications/tools-scripts/llm/deepseek_review_adapter.py` | Adapter that emits the answer / receipt pair |
+| `5-Applications/tools-scripts/llm/deepseek_review_adapter.py` | Related Anthropic-compatible DeepSeek adapter; it does not emit the current Ollama-style receipt schema |

shared-data/artifacts/deepseek_review/prime_gap_entropy_collapse_deepseek_deepseek-v3.2_20260512T033551Z.receipt.json

@@ -4,7 +4,7 @@
   "model": "deepseek-v3.2",
   "endpoint": "https://ollama.com/v1/chat/completions",
   "prompt_sha256": "sha256:41d0d6e83f36bee093b5ac992b7b29ff7657bc33e0dce0e684e1d3ddc679ee92",
-  "answer_sha256": "sha256:8f12e758a3dcce56982e1ffdff99e31cfa4cf071afc8b7ed8d348972af9536c7",
+  "answer_sha256": "sha256:81fe9e97f9de62ea4adc852185f7d85424ce6476f5b7f158106806bffddf6303",
   "usage": {
     "prompt_tokens": 5008,
     "completion_tokens": 5000,
@@ -16,4 +16,4 @@
     "0-Core-Formalism/lean/Semantics/Semantics/HCMMR/Kernels/EntropyCollapseDetector.lean"
   ],
   "answer_path": "shared-data/artifacts/deepseek_review/prime_gap_entropy_collapse_deepseek_deepseek-v3.2_20260512T033551Z.md"
-}
+}

shared-data/artifacts/deepseek_review/prime_gap_entropy_collapse_deepseek_deepseek-v4-flash_continuation_20260512T033849Z.receipt.json

@@ -4,7 +4,7 @@
   "model": "deepseek-v4-flash",
   "endpoint": "https://ollama.com/v1/chat/completions",
   "prompt_sha256": "sha256:2369eeb5ae11dfa345452e0b9f35fe06e7f6779d47dabcf4eb12e6a8217285b0",
-  "answer_sha256": "sha256:883da3ced92768523d6b640ec242f13eb8feb98d3af3118d899a14ba9c18727c",
+  "answer_sha256": "sha256:9c7b6cc5bd76f986302b8bc973ad23aca7850103d5a76b6b9ae10fdc4d7236a6",
   "usage": {
     "prompt_tokens": 372,
     "completion_tokens": 440,
@@ -17,4 +17,4 @@
   ],
   "previous_answer_path": "shared-data/artifacts/deepseek_review/prime_gap_entropy_collapse_deepseek_deepseek-v3.2_20260512T033551Z.md",
   "answer_path": "shared-data/artifacts/deepseek_review/prime_gap_entropy_collapse_deepseek_deepseek-v4-flash_continuation_20260512T033849Z.md"
-}
+}